© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41450
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    This neuron activates on words expressing probability or likelihood (e.g. “Chances,” “Odds”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raspberry
    -0.07
    证
    -0.06
     warriors
    -0.06
    >alert
    -0.06
     blend
    -0.06
    들
    -0.06
     mushroom
    -0.06
     DOCUMENT
    -0.06
     harmless
    -0.06
     môi
    -0.06
    POSITIVE LOGITS
     نویس
    0.06
     ^{°}
    0.06
    ]*
    0.06
     Banc
    0.06
    orno
    0.06
     Are
    0.06
     Economic
    0.06
     Services
    0.06
     knocks
    0.06
    .tx
    0.06
    Activations Density 0.035%

    No Known Activations